24 product demo recordings of 8 minutes: transcript cost

Transcribing 24 product demos of 8 minutes each is 192 audio minutes, or 3.2 hours, which costs $1.73 on MAI-Transcribe-2-Streaming ($1.728 before rounding) and $1.92 on Sume STT 1.0, one job per demo.

At 8 minutes each, every demo fits one Sume job with two minutes of headroom.

The arithmetic

MAI-Transcribe-2-Streaming is priced per hour, Sume STT 1.0 per audio minute, so the sums convert minutes to hours first. The Sume rate is the public rate on the Sume docs; confirm the live number in GET /v1/catalog.

Per minute, MAI works out to $0.009 ($0.54 / 60) against Sume's $0.01, so Sume is about 11 percent higher. On this run the difference is $0.192. Microsoft's rate is an introductory price that its page says runs through the end of the year, and the page does not say what the price becomes afterward, so a budget past December should not assume it.

Turning transcripts into docs

Ask for segmentation with mode sentence so each demo comes back as sentence segments with start and end times, which map cleanly to doc paragraphs.

A transcript costs 8 cents a demo, so re-running one after a re-record is cheap.

• Pass language_code when the demo is not English; omitting it uses auto-detect.
• Proofread product names; the STT request has no vocabulary field.

Limits that shape a Sume run

Sume does not list MAI-Transcribe-2-Streaming, so the MAI row is a price reference. Sume STT 1.0 takes a public HTTPS audio_url and returns the transcript with word timings; there is no flag for timings because they always come back. Sentence segments are available when you send segmentation.

• duration_seconds is an optional hint from 1 to 600; leave it out and Sume reserves one minute, so send it for a long file.
• language_code is a hint such as en or ko; leave it out for auto-detect.
• diarize and tag_audio_events are fixed server-side, so do not send them; there are no speaker-label controls.
• The MAI price is an introductory rate that Microsoft says runs through the end of the year.

Running it

Submit with stt_create and an idempotency_key, wait with jobs_wait, then read jobs_result for the text and words. Cut recordings longer than 10 minutes at a pause first; audio detach pulls the track out of a video and Timeline audio split slices a Sume-hosted file into ranges.

The figures are list arithmetic as of 2026-10-08. A one-time check of your own audio is worth more than a benchmark, so run one representative file through each option before you commit a budget.